Merge pull request #307 from sterling-teng/linux-6.6.y

LoongArch: Add kernel livepatching support

Author: Avenger-285714

arch/loongarch/Kconfig

@@ -133,18 +133,22 @@ config LOONGARCH
 	select HAVE_KPROBES_ON_FTRACE
 	select HAVE_KRETPROBES
 	select HAVE_KVM
+	select HAVE_LIVEPATCH
 	select HAVE_MOD_ARCH_SPECIFIC
 	select HAVE_NMI
+	select HAVE_OBJTOOL if AS_HAS_EXPLICIT_RELOCS
 	select HAVE_PCI
 	select HAVE_PERF_EVENTS
 	select HAVE_PERF_REGS
 	select HAVE_PERF_USER_STACK_DUMP
 	select HAVE_REGS_AND_STACK_ACCESS_API
+	select HAVE_RELIABLE_STACKTRACE if UNWINDER_ORC
 	select HAVE_RETHOOK
 	select HAVE_RSEQ
 	select HAVE_SAMPLE_FTRACE_DIRECT
 	select HAVE_SAMPLE_FTRACE_DIRECT_MULTI
 	select HAVE_SETUP_PER_CPU_AREA if NUMA
+	select HAVE_STACK_VALIDATION if HAVE_OBJTOOL
 	select HAVE_STACKPROTECTOR
 	select HAVE_SYSCALL_TRACEPOINTS
 	select HAVE_TIF_NOHZ
@@ -619,6 +623,8 @@ config RANDOMIZE_BASE_MAX_OFFSET
 
 	  This is limited by the size of the lower address memory, 256MB.
 
+source "kernel/livepatch/Kconfig"
+
 endmenu
 
 config ARCH_SELECT_MEMORY_MODEL

arch/loongarch/Kconfig.debug

@@ -26,4 +26,15 @@ config UNWINDER_PROLOGUE
 	  Some of the addresses it reports may be incorrect (but better than the
 	  Guess unwinder).
 
+config UNWINDER_ORC
+	bool "ORC unwinder"
+	select OBJTOOL
+	help
+	  This option enables the ORC (Oops Rewind Capability) unwinder for
+	  unwinding kernel stack traces.  It uses a custom data format which is
+	  a simplified version of the DWARF Call Frame Information standard.
+
+	  Enabling this option will increase the kernel's runtime memory usage
+	  by roughly 2-4MB, depending on your kernel config.
+
 endchoice

arch/loongarch/Makefile

@@ -25,6 +25,18 @@ endif
 32bit-emul		= elf32loongarch
 64bit-emul		= elf64loongarch
 
+ifdef CONFIG_UNWINDER_ORC
+orc_hash_h := arch/$(SRCARCH)/include/generated/asm/orc_hash.h
+orc_hash_sh := $(srctree)/scripts/orc_hash.sh
+targets += $(orc_hash_h)
+quiet_cmd_orc_hash = GEN     $@
+      cmd_orc_hash = mkdir -p $(dir $@); \
+		     $(CONFIG_SHELL) $(orc_hash_sh) < $< > $@
+$(orc_hash_h): $(srctree)/arch/loongarch/include/asm/orc_types.h $(orc_hash_sh) FORCE
+	$(call if_changed,orc_hash)
+archprepare: $(orc_hash_h)
+endif
+
 ifdef CONFIG_DYNAMIC_FTRACE
 KBUILD_CPPFLAGS += -DCC_USING_PATCHABLE_FUNCTION_ENTRY
 CC_FLAGS_FTRACE := -fpatchable-function-entry=2
@@ -68,8 +80,6 @@ LDFLAGS_vmlinux			+= -static -n -nostdlib
 ifdef CONFIG_AS_HAS_EXPLICIT_RELOCS
 cflags-y			+= $(call cc-option,-mexplicit-relocs)
 KBUILD_CFLAGS_KERNEL		+= $(call cc-option,-mdirect-extern-access)
-KBUILD_AFLAGS_MODULE		+= $(call cc-option,-mno-relax) $(call cc-option,-Wa$(comma)-mno-relax)
-KBUILD_CFLAGS_MODULE		+= $(call cc-option,-mno-relax) $(call cc-option,-Wa$(comma)-mno-relax)
 else
 cflags-y			+= $(call cc-option,-mno-explicit-relocs)
 KBUILD_AFLAGS_KERNEL		+= -Wa,-mla-global-with-pcrel
@@ -78,6 +88,15 @@ KBUILD_AFLAGS_MODULE		+= -Wa,-mla-global-with-abs
 KBUILD_CFLAGS_MODULE		+= -fplt -Wa,-mla-global-with-abs,-mla-local-with-abs
 endif
 
+KBUILD_AFLAGS			+= $(call cc-option,-mno-relax) $(call cc-option,-Wa$(comma)-mno-relax)
+KBUILD_CFLAGS			+= $(call cc-option,-mno-relax) $(call cc-option,-Wa$(comma)-mno-relax)
+KBUILD_AFLAGS			+= $(call cc-option,-mthin-add-sub) $(call cc-option,-Wa$(comma)-mthin-add-sub)
+KBUILD_CFLAGS			+= $(call cc-option,-mthin-add-sub) $(call cc-option,-Wa$(comma)-mthin-add-sub)
+
+ifdef CONFIG_OBJTOOL
+KBUILD_CFLAGS			+= -fno-jump-tables
+endif
+
 ifeq ($(CONFIG_RELOCATABLE),y)
 KBUILD_CFLAGS_KERNEL		+= -fPIE
 LDFLAGS_vmlinux			+= -static -pie --no-dynamic-linker -z notext $(call ld-option, --apply-dynamic-relocs)

arch/loongarch/include/asm/Kbuild

@@ -1,4 +1,6 @@
 # SPDX-License-Identifier: GPL-2.0
+generated-y += orc_hash.h
+
 generic-y += dma-contiguous.h
 generic-y += mcs_spinlock.h
 generic-y += parport.h

arch/loongarch/include/asm/bug.h

@@ -44,6 +44,7 @@
 do {								\
 	instrumentation_begin();				\
 	__BUG_FLAGS(BUGFLAG_WARNING|(flags));			\
+	annotate_reachable();					\
 	instrumentation_end();					\
 } while (0)
 

arch/loongarch/include/asm/exception.h

@@ -6,6 +6,8 @@
 #include <asm/ptrace.h>
 #include <linux/kprobes.h>
 
+extern void *exception_table[];
+
 void show_registers(struct pt_regs *regs);
 
 asmlinkage void cache_parity_error(void);

arch/loongarch/include/asm/ftrace.h

@@ -63,7 +63,7 @@ ftrace_regs_get_instruction_pointer(struct ftrace_regs *fregs)
 static __always_inline void
 ftrace_regs_set_instruction_pointer(struct ftrace_regs *fregs, unsigned long ip)
 {
-	regs_set_return_value(&fregs->regs, ip);
+	instruction_pointer_set(&fregs->regs, ip);
 }
 
 #define ftrace_regs_get_argument(fregs, n) \

arch/loongarch/include/asm/module.h

@@ -6,6 +6,7 @@
 #define _ASM_MODULE_H
 
 #include <asm/inst.h>
+#include <asm/orc_types.h>
 #include <asm-generic/module.h>
 
 #define RELA_STACK_DEPTH 16
@@ -21,6 +22,12 @@ struct mod_arch_specific {
 	struct mod_section plt;
 	struct mod_section plt_idx;
 
+#ifdef CONFIG_UNWINDER_ORC
+	unsigned int num_orcs;
+	int *orc_unwind_ip;
+	struct orc_entry *orc_unwind;
+#endif
+
 	/* For CONFIG_DYNAMIC_FTRACE */
 	struct plt_entry *ftrace_trampolines;
 };

arch/loongarch/include/asm/orc_header.h

@@ -0,0 +1,18 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+
+#ifndef _ORC_HEADER_H
+#define _ORC_HEADER_H
+
+#include <linux/types.h>
+#include <linux/compiler.h>
+#include <asm/orc_hash.h>
+
+/*
+ * The header is currently a 20-byte hash of the ORC entry definition; see
+ * scripts/orc_hash.sh.
+ */
+#define ORC_HEADER					\
+	__used __section(".orc_header") __aligned(4)	\
+	static const u8 orc_header[] = { ORC_HASH }
+
+#endif /* _ORC_HEADER_H */

arch/loongarch/include/asm/orc_lookup.h

@@ -0,0 +1,31 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+#ifndef _ORC_LOOKUP_H
+#define _ORC_LOOKUP_H
+
+/*
+ * This is a lookup table for speeding up access to the .orc_unwind table.
+ * Given an input address offset, the corresponding lookup table entry
+ * specifies a subset of the .orc_unwind table to search.
+ *
+ * Each block represents the end of the previous range and the start of the
+ * next range.  An extra block is added to give the last range an end.
+ *
+ * The block size should be a power of 2 to avoid a costly 'div' instruction.
+ *
+ * A block size of 256 was chosen because it roughly doubles unwinder
+ * performance while only adding ~5% to the ORC data footprint.
+ */
+#define LOOKUP_BLOCK_ORDER	8
+#define LOOKUP_BLOCK_SIZE	(1 << LOOKUP_BLOCK_ORDER)
+
+#ifndef LINKER_SCRIPT
+
+extern unsigned int orc_lookup[];
+extern unsigned int orc_lookup_end[];
+
+#define LOOKUP_START_IP		(unsigned long)_stext
+#define LOOKUP_STOP_IP		(unsigned long)_etext
+
+#endif /* LINKER_SCRIPT */
+
+#endif /* _ORC_LOOKUP_H */